Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to cultural expectations and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thereof
    -0.15
    aycast
    -0.15
     εÏĢίÏĥηÏĤ
    -0.14
    .jackson
    -0.14
    anj
    -0.13
    893
    -0.13
     jich
    -0.13
    صر
    -0.13
    hra
    -0.13
    ãĥ¼ãĤ¸
    -0.12
    POSITIVE LOGITS
    boro
    0.14
    ORY
    0.13
    ENU
    0.13
     .
    0.13
    oooo
    0.13
    ined
    0.12
     absolutely
    0.12
     eigentlich
    0.12
    TERN
    0.12
     whenever
    0.12
    Act Density 0.893%

    No Known Activations